Skip to content

GitLab

You need to sign in or sign up before continuing.
Unverified Commit f7278638 authored by Will Berman's avatar Will Berman Committed by GitHub
Browse files

ema step, don't empty cuda cache (#2563)

parent b36cbd4f
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 2 deletions
src/diffusers/training_utils.py
View file @ f7278638
...@@ -203,8 +203,6 @@ class EMAModel: ...@@ -203,8 +203,6 @@ class EMAModel:
else: else:
s_param.copy_(param) s_param.copy_(param)
torch.cuda.empty_cache()
def copy_to(self, parameters: Iterable[torch.nn.Parameter]) -> None: def copy_to(self, parameters: Iterable[torch.nn.Parameter]) -> None:
""" """
Copy current averaged parameters into given collection of parameters. Copy current averaged parameters into given collection of parameters.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment